LLM KV cache compression made easy

🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents

Self-referential self-improving agents that can optimize for any computable task

"OpenSpace: Make Your Agents: Smarter, Low-Cost, Self-Evolving" -- Community: https://open-space.cloud/

Make your OpenClaw agent self-improving

This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding code links.

[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

🚀 The fast, Pythonic way to build MCP servers and clients.

Open-source unified multimodal model

我在 Obsidian 中用的各种模板（Dataview，Templater，QuickAdd）

DFlash: Block Diffusion for Flash Speculative Decoding

[ICLR'26] Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling

Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)

WeDLM: The fastest diffusion language model with standard causal attention and native KV cache compatibility, delivering real speedups over vLLM-optimized baselines.

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

Persist and reuse KV Cache to speedup your LLM.

Auto get diffusion nlp papers in Axriv. More papers Information can be found in another repository "Diffusion-LM-Papers".

The code for "AttentionPredictor: Temporal Pattern Matters for Efficient LLM Inference", Qingyue Yang, Jie Wang, Xing Li, Zhihai Wang, Chen Chen, Lei Chen, Xianzhi Yu, Wulong Liu, Jianye HAO, Mingx…

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference

Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

[NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.

An autonomous agent that conducts deep research on any data using any LLM providers

Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …

Naive Bayes-based Context Extension

The agent engineering platform. Available in TypeScript!

Mass-editing thousands of facts into a transformer memory (ICLR 2023)

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

Instruct-tune LLaMA on consumer hardware